Improved Sequence Classification Using Adaptive Segmental Sequence Alignment

Shahriar Shariat, Vladimir Pavlovic
Proceedings of the Asian Conference on Machine Learning, PMLR 25:379-394, 2012.

Abstract

Traditional pairwise sequence alignment is based on matching individual samples from two sequences, under time monotonicity constraints. However, in some instances matching two segments of points may be preferred and can result in increased noise robustness. This paper presents an approach to segmental sequence alignment based on adaptive pairwise segmentation. We introduce a distance metric between segments based on average pairwise distances, which addresses deficiencies of prior approaches. We then present a modified pair-HMM that incorporates the proposed distance metric and use it to devise an e¡cient algorithm to jointly segment and align the two sequences. Our results demonstrate that this new measure of sequence similarity can lead to improved classification performance, while being resilient to noise, on a variety of problems, from EEG to motion sequence classification.

Cite this Paper

BibTeX
@InProceedings{pmlr-v25-shariat12, title = {Improved Sequence Classification Using Adaptive Segmental Sequence Alignment}, author = {Shariat, Shahriar and Pavlovic, Vladimir}, booktitle = {Proceedings of the Asian Conference on Machine Learning}, pages = {379--394}, year = {2012}, editor = {Hoi, Steven C. H. and Buntine, Wray}, volume = {25}, series = {Proceedings of Machine Learning Research}, address = {Singapore Management University, Singapore}, month = {04--06 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v25/shariat12/shariat12.pdf}, url = {https://proceedings.mlr.press/v25/shariat12.html}, abstract = {Traditional pairwise sequence alignment is based on matching individual samples from two sequences, under time monotonicity constraints. However, in some instances matching two segments of points may be preferred and can result in increased noise robustness. This paper presents an approach to segmental sequence alignment based on adaptive pairwise segmentation. We introduce a distance metric between segments based on average pairwise distances, which addresses deficiencies of prior approaches. We then present a modified pair-HMM that incorporates the proposed distance metric and use it to devise an e¡cient algorithm to jointly segment and align the two sequences. Our results demonstrate that this new measure of sequence similarity can lead to improved classification performance, while being resilient to noise, on a variety of problems, from EEG to motion sequence classification.} }
Endnote
%0 Conference Paper %T Improved Sequence Classification Using Adaptive Segmental Sequence Alignment %A Shahriar Shariat %A Vladimir Pavlovic %B Proceedings of the Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2012 %E Steven C. H. Hoi %E Wray Buntine %F pmlr-v25-shariat12 %I PMLR %P 379--394 %U https://proceedings.mlr.press/v25/shariat12.html %V 25 %X Traditional pairwise sequence alignment is based on matching individual samples from two sequences, under time monotonicity constraints. However, in some instances matching two segments of points may be preferred and can result in increased noise robustness. This paper presents an approach to segmental sequence alignment based on adaptive pairwise segmentation. We introduce a distance metric between segments based on average pairwise distances, which addresses deficiencies of prior approaches. We then present a modified pair-HMM that incorporates the proposed distance metric and use it to devise an e¡cient algorithm to jointly segment and align the two sequences. Our results demonstrate that this new measure of sequence similarity can lead to improved classification performance, while being resilient to noise, on a variety of problems, from EEG to motion sequence classification.
RIS
TY - CPAPER TI - Improved Sequence Classification Using Adaptive Segmental Sequence Alignment AU - Shahriar Shariat AU - Vladimir Pavlovic BT - Proceedings of the Asian Conference on Machine Learning DA - 2012/11/17 ED - Steven C. H. Hoi ED - Wray Buntine ID - pmlr-v25-shariat12 PB - PMLR DP - Proceedings of Machine Learning Research VL - 25 SP - 379 EP - 394 L1 - http://proceedings.mlr.press/v25/shariat12/shariat12.pdf UR - https://proceedings.mlr.press/v25/shariat12.html AB - Traditional pairwise sequence alignment is based on matching individual samples from two sequences, under time monotonicity constraints. However, in some instances matching two segments of points may be preferred and can result in increased noise robustness. This paper presents an approach to segmental sequence alignment based on adaptive pairwise segmentation. We introduce a distance metric between segments based on average pairwise distances, which addresses deficiencies of prior approaches. We then present a modified pair-HMM that incorporates the proposed distance metric and use it to devise an e¡cient algorithm to jointly segment and align the two sequences. Our results demonstrate that this new measure of sequence similarity can lead to improved classification performance, while being resilient to noise, on a variety of problems, from EEG to motion sequence classification. ER -
APA
Shariat, S. & Pavlovic, V.. (2012). Improved Sequence Classification Using Adaptive Segmental Sequence Alignment. Proceedings of the Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 25:379-394 Available from https://proceedings.mlr.press/v25/shariat12.html.

Related Material